A Structure-Enriched Neural Network for network embedding

•A structure-enriched framework for network embedding from a holistic perspective.•Introducing the direction tuning parameters into multi-order transition matrices.•Using the denoise autoencoder to do the dimension reduction of multi-order matrices.•Employing the method with attention mechanism to c...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Expert systems with applications Ročník 117; s. 300 - 311
Hlavní autoři: Qiao, Lisheng, Zhao, Hongke, Huang, Xiaohui, Li, Kai, Chen, Enhong
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Elsevier Ltd 01.03.2019
Elsevier BV
Témata:
Algorithms
Attention mechanism
Direction adjustment
Embedding
Matrix
Network embedding
Neural networks
Noise reduction
Probability
State of the art
Topology
Transportation networks
Direction adjustment
Attention mechanism
Network embedding
ISSN:0957-4174, 1873-6793
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•A structure-enriched framework for network embedding from a holistic perspective.•Introducing the direction tuning parameters into multi-order transition matrices.•Using the denoise autoencoder to do the dimension reduction of multi-order matrices.•Employing the method with attention mechanism to combine multi-order information. Recent years have witnessed the importance of network embedding in many fields, as well as increased attention in academia. Although a number of algorithms have been proposed in this area, most existing models which only utilize the structure topology information of networks often suffer performance losses because of their insufficiency with regard to selecting structure similar patterns, handling noise data, and/or capturing non-linear or high-order structure information. To address these challenges, in this paper, we present a novel Structure-Enriched Neural Network (SENN) for network embedding. Specifically, SENN can not only capture the complex structure similar patterns observed in networks by introducing direction adjustment parameters of the transition probability, but also introduce a stacked denoise autoencoder to perform the dimension reduction for each order matrix independently. Therefore, SENN can preserve more useful structure information and make the embeddings more robust. Moreover, SENN can effectively integrate the multi-order structure information by the combining layer with attention mechanism. Finally, to compare with other state-of-the-art methods, we conduct extensive experiments with both synthetic and real-world datasets on various tasks (e.g.,node classification, visualization). The experimental results clearly demonstrate the effectiveness of our proposed model for network embedding.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0957-4174
1873-6793
DOI:10.1016/j.eswa.2018.09.040